© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3444
    Prev
    Next
    INDEX
    Explanations

    geometric shapes

    np_acts-logits-general · gemini-2.5-flash-lite

    geometric shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    潞
    0.43
    妥
    0.42
     живу
    0.40
     kapsam
    0.39
     नेते
    0.39
     residentes
    0.38
    ძლი
    0.37
    暧
    0.37
    䙲
    0.37
    দ্দীন
    0.37
    POSITIVE LOGITS
     rectangular
    3.06
    rectangular
    2.81
     oval
    2.70
     cylindrical
    2.61
    圆形
    2.61
     circular
    2.58
     triangular
    2.53
     oblong
    2.44
     rectangle
    2.42
     прямоуго
    2.41
    Activations Density 0.390%

    No Known Activations